Legal claims defining the scope of protection, as filed with the USPTO.
1. A method, comprising: obtaining, by a computer system with one or more processors coupled with at least one memory unit, a target audio stream from a target and an agent audio stream from an agent when the agent is engaging in a conversation with the target, wherein the conversation is a persuasion attempt for a first object; obtaining an agent content output and a target content output by analyzing the agent audio stream and the target audio stream using a recurrent network (RNN) model; obtaining an agent sentiment classifier for the agent audio stream and a target sentiment classifier for the target audio stream, wherein each sentiment classifier is derived from an emotion classifier resulting from a convolutional neural network (CNN) model analysis of a corresponding audio stream; updating a conversation matrix that contains prior and current audio stream analysis based on prior and current content outputs and sentiment classifiers for the agent and the target; generating a persuasion reference based on the updated conversation matrix.
2. The method of claim 1 , wherein the persuasion reference is based on an acceptance likelihood result generated from the conversation matrix using the RNN model.
3. The method of claim 1 , wherein the persuasion reference includes one or more guidance comprising: reference materials of the first object, guidance materials of the first object, suggestion of voice sentiments change for the agent, and one or more suggested new objects.
4. The method of claim 3 , wherein the one or more guidance in the persuasion reference is ranked.
5. The method of claim 3 , wherein the one or more suggested new objects are generated using a CNN with input from subject Big Data that is associated with the first object.
6. The method of claim 1 , wherein the persuasion reference is generated further based on one or more prior persuasion references.
7. The method of claim 6 , wherein the conversation matrix indicates that a list of guidance on the one or more prior persuasion references is not followed.
8. The method of claim 1 , wherein the emotion classifier is one selecting from an emotion group comprising angry emotion, excited emotion, frustrated emotion, happy emotion, neutral emotion, sad emotion, and surprised emotion, and the sentiment classifier is one selecting from a sentiment group comprising extremely positive, positive, neutral, negative, extremely negative, and surprised.
9. The method of claim 1 , further comprising: generating a target profile using CNN with input of target Big Data, wherein the target profile includes one or more objects, and wherein the agent is selected based on the generated profile and one or more selected objects.
10. The method of claim 1 , wherein the persuasion reference is delivered to a mobile device used by the agent through content streaming.
11. A system comprising: an audio input module that obtains a target audio stream from a target and an agent audio stream from an agent when the agent is engaging in a conversation with the target, wherein the conversation is a persuasion attempt for a first object; a content output module that obtains an agent content output and a target content output by analyzing the agent audio stream and the target audio stream using a recurrent network (RNN) model; a speech classifier module that obtains an agent sentiment classifier for the agent audio stream and a target sentiment classifier for the target audio stream, wherein each sentiment classifier is derived from an emotion classifier resulting from a convolutional neural network (CNN) model analysis of a corresponding audio stream; a conversation handling module that updates a conversation matrix that contains prior and current audio stream analysis based on prior and current content outputs and sentiment classifiers for the agent and the target; a persuasion reference module that generates a persuasion reference based on the updated conversation matrix.
12. The system of claim 11 , wherein the persuasion reference is based on an acceptance likelihood result generated from the conversation matrix using the RNN model.
13. The system of claim 11 , wherein the persuasion reference includes one or more guidance comprising: reference materials of the first object, guidance materials of the first object, suggestion of voice sentiments change for the agent, and one or more suggested new objects.
14. The system of claim 13 , wherein the one or more guidance in the persuasion reference is ranked.
15. The system of claim 13 , wherein the one or more suggested new objects are generated using a CNN with input from subject Big Data that is associated with the first object.
16. The system of claim 11 , wherein the persuasion reference is generated further based on one or more prior persuasion references.
17. The system of claim 16 , wherein the conversation matrix indicates that a list of guidance on the one or more prior persuasion references is not followed.
18. The system of claim 11 , wherein the emotion classifier is one selecting from an emotion group comprising angry emotion, excited emotion, frustrated emotion, happy emotion, neutral emotion, sad emotion, and surprised emotion, and the sentiment classifier is one selecting from a sentiment group comprising extremely positive, positive, neutral, negative, extremely negative, and surprised.
19. The system of claim 11 , wherein the persuasion reference is delivered to a mobile device used by the agent through content streaming.
20. The system of claim 11 , further comprising: a profile module that generates a target profile using CNN with input of target Big Data, wherein the target profile includes one or more objects, and wherein the agent is selected based on the generated profile and one or more selected objects.
Unknown
June 29, 2021
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.